Unverified50% confidenceBenchmarkExact time
There are 33 technical errors in the dataset; the largest cluster is the Qwen 3.5 35B-A3B configuration, with 22 errors out of 32 attempts.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedClaude Haiku 4.5 answered 'not found' in 21 of its 24 errors on two-step questions, while GPT-5.4 mini copied the literal wording of the referral as the answer in 20 of its 27 errors, and fabricated real-sounding names while citing actual documents in another 7.70% similarUnverifiedIn Artificial Analysis's complex capability leaderboard, Qwen3-VL 27B ranks 26th among more than 600 models.67% similarUnverifiedAccording to the ISO/IEC 18004 standard, QR codes define 40 size levels ranging from Version 1 (21×21 modules) to Version 40 (177×177 modules), as well as four error correction levels: L, M, Q, and H.65% similarUnverifiedOfficial benchmark data shows that the new version of Qwen3 27B agent coding improved from 13.3 to 42.2, software engineering tasks improved from 49.3 to 79, and frontier agent tasks improved from 10.6 to 20.64% similarUnverified46个模型中有41个完整跑完全部28道题，3个因服务错误未完成，GPT-5.6 Terra因配额限制止步24/28，GPT-6 Astra只跑了1道题64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003733API
curl https://kongchang.com/api/v1/knowledge/claims/1003733MCP
get_claim(id=1003733)